Abstract
We present PARDISO, a new parallel sparse direct linear solver for large-scale parallel semiconductor device and process simulations on shared memory multiprocessors. Since robust transient 2-D and 3-D simulations necessitate large computing resources, the choice of architectures, algorithms and their implementations becomes of utmost importance. Sparse direct methods are the most robust methods over a wide range of numerical properties and therefore PARDISO has been integrated into complex semiconductor device and process simulation packages. We have investigated popular shared memory multiprocessors and the most popular numerical algorithms commonly used for the solution of the classical drift-diffusion and the diffusion-reaction equations in process simulation. The study includes a preconditioned iterative linear solver package and our parallel direct linear solver. Moreover, we have investigated the efficiency and the limits of our parallel approach. Results of several simulations of up to 100’000 vertices for three-dimensional device simulations are presented to illustrate our approach towards robust, parallel semiconductor device and process simulation.
Article Footnote
The work of O. Schenk was supported by a grant from the Cray Research and Development Grant Program and the Swiss Commission of Technology and Innovation (KTI) under contract number 3975.1.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
C. Ashcraft, R. Grimes, J. Lewis, B. Peyton, and H. Simon. Progress in sparse matrix methods for large linear systems on vector supercomputers. The International Journal of Supercomputer Applications, 1(4):10–30, 1987.
R. Barrett, M. Berry, T. Chan, J. Demmel, J. Donato, J. Dongarra, V. Eijkhout, R. Pozo, C. Romine, and H. van der Vorst. Templates for the solution of linear systems: building blocks for iterative methods. SIAM, 1994.
J. Demmel, J. Gilbert, and X. Li. An asynchronous parallel supernodal algorithm to sparse partial pivoting. Technical Report CSD-97–943, University of California at Berkeley, Feb. 1997, 1997. To appear in SIAM J. Matrix Anal. Appl.
I. Duff, A. Erisman, and J.K. Reid. Direct methods for sparse matrices. Oxford Science Publications, 1986.
D. Fokkema. Subspace methods for linear, nonlinear, and eigen problems. PhD thesis, Utrecht University, 1996.
A. George and J. Liu. Computer solution of large sparse positive definite systems. Prentice-Hall, 1981.
G. Golub and C. van Loan. Matrix computations. The John Hopkins University Press, 3nd edition, 1996.
G. Heiser, C. Pommerell, J. Weis, and W. Fichtner. Three-dimensional numerical semiconductor device simulation: Algorithms, architectures, results. IEEE Transactions on Computer-Aided Design,10(10):1218–1230, 1991.
Integrated Systems Engineering AG. DESSIS_ISE Reference Manual. ISE Integrated Systems Engineering AG, 1998.
Integrated Systems Engineering AG. DIOS_ISE Reference Manual. ISE Integrated Systems Engineering AG, 1998.
Integrated Systems Engineering AG. SLIP90_ISE Reference Manual. ISE Integrated Systems Engineering AG, 1998.
Integrated Systems Engineering AG. SUPER_ISE Reference Manual. ISE Integrated Systems Engineering AG, 1998.
G. Karypis and V. Kumar. Analysis of multilevel graph algorithms. Technical Report MN 95–037, University of Minnesota, Department of Computer Science, Minneapolis, MN 55455, 1995.
G. Karypis and V. Kumar. Multilevel algorithms for multi-constraint graph partitioning. Technical Report MN 98–019, University of Minnesota, Department of Computer Science, Minneapolis, MN 55455, 1998.
C. Lawson, R. Hanson, D. Kincaid, and F. Krogh. Basic linear algebra subprograms for Fortran usage. ACM Transactions on Mathematical Software, 5(3):308–325, 1979.
A. Liegmann. Efficient Solution of Large Sparse Linear Systems. PhD thesis, ETH Zürich, 1995.
J. Liu. Modification of the Minimum-Degree algorithm by multiple elimination. ACM Transactions on Mathematical Software, 11(2):141–153, 1985.
J. Liu, E. Ng, and B. Peyton. On finding supernodes for sparse matrix computations. Technical Report TM-11563, Oak Ridge National Laboratory, 1990.
E. Ng and B. Peyton. A supernodal Cholesky factorization algorithm for shared-memory multiprocessors. SIAM Journal on Scientific Computing, 14(4):761–769,1993.
A. Pothen, H. Simon, and K. Liou. Partitioning sparse matrices with eigenvectors of graphs. SIAM Journal on Matrix Analysis & Applications, 11(3): 430–452, July 1990.
Y. Saad. Iterative Methods for Sparse Linear Systems. PWS Publishing Company, 1996.
O. Schenk, K. Gärtner, and W. Fichtner. Efficient sparse LU factorization with left-right looking strategy on shared memory multiprocessors. Technical Report 98/40, Integrated Systems Laboratory, ETH Zurich, Swiss Fed. Inst. of Technology (ETH), Zurich, Switzerland, Submitted to BIT Numerical Mathematics, 1998.
O. Schenk, K. Gärtner, and W. Fichtner. Parallel sparse LU factorization in a shared memory computing environment. In The proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA’98), pages 907–914, 1998.
A. Sherman. On the efficient solution of sparse linear and nonlinear equations. PhD thesis, Yale University, New Haven, CT, 1975.
G. Sleijpen, H. van der Vorst, and D. Fokkema. BiCGSTAB(1) and other hybrid Bi-CG methods. Technical Report TR Nr. 831, Department of Mathematics, University Utrecht, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer Science+Business Media New York
About this chapter
Cite this chapter
Schenk, O., Gärtner, K., Schmithüsen, B., Fichtner, W. (1999). Numerical Semiconductor Device and Process Simulation on Shared Memory Multiprocessors: Algorithms, Architectures, Results. In: Yang, T. (eds) Parallel Numerical Computation with Applications. The Springer International Series in Engineering and Computer Science, vol 515. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5205-5_10
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5205-5_10
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7371-1
Online ISBN: 978-1-4615-5205-5
eBook Packages: Springer Book Archive